计算机科学
语义学(计算机科学)
人工智能
失真(音乐)
水下
计算机视觉
特征(语言学)
背景(考古学)
图像复原
透视图(图形)
模式识别(心理学)
语义特征
图像(数学)
感知
图像质量
GSM演进的增强数据速率
特征提取
透视失真
可视化
身份(音乐)
质量(理念)
噪音(视频)
发电机(电路理论)
面子(社会学概念)
图像增强
图像处理
作者
Yu Meng,Liquan Shen,Yihan Yu,Yu Zhang,Rui Le
标识
DOI:10.1109/tip.2025.3647323
摘要
Underwater image enhancement (UIE) is crucial for robust marine exploration, yet existing methods prioritize perceptual quality while overlooking irreversible semantic corruption that impairs downstream tasks. Unlike terrestrial images, underwater semantics exhibit layer-specific degradations: shallow features suffer from color shifts and edge erosion, while deep features face semantic ambiguity. These distortions entangle with semantic content across feature hierarchies, where direct enhancement amplifies interference in downstream tasks. Even if distortions are removed, the damaged semantic structures cannot be fully recovered, making it imperative to further enhance corrupted content. To address these challenges, we propose a task-driven UIE framework that redefines enhancement as machine-interpretable semantic recovery rather than mere distortion removal. First, we introduce a multi-scale underwater distortion-aware generator to perceive distortions across feature levels and provide a prior for distortion removal. Second, leveraging this prior and the absence of clean underwater references, we propose a stable self-supervised disentanglement strategy to explicitly separate distortions from corrupted content through CLIP-based semantic constraints and identity consistency. Finally, to compensate for the irreversible semantic loss, we design a task-aware hierarchical enhancement module that refines shallow details via spatial-frequency fusion and strengthens deep semantics through multi-scale context aggregation, aligning results with machine vision requirements. Extensive experiments on segmentation, detection, and saliency tasks demonstrate the superiority of our method in restoring machine-friendly semantics from degraded underwater images. Our code is available at https://github.com/gemyumeng/HSRUIE.
科研通智能强力驱动
Strongly Powered by AbleSci AI